scholarly journals Modified U-Net for liver cancer segmentation from computed tomography images with a new class balancing method

2021 ◽  
Vol 3 (1) ◽  
Author(s):  
Yodit Abebe Ayalew ◽  
Kinde Anlay Fante ◽  
Mohammed Aliy Mohammed
Keyword(s):  
Computed Tomography ◽  
Deep Learning ◽  
Liver Cancer ◽  
Ct Scan ◽  
Tumor Segmentation ◽  
Class Imbalance Problem ◽  
Abdominal Ct ◽  
New Class ◽  
Computed Tomography Images ◽  
Abdominal Ct Scan

Abstract Background Liver cancer is the sixth most common cancer worldwide. It is mostly diagnosed with a computed tomography scan. Nowadays deep learning methods have been used for the segmentation of the liver and its tumor from the computed tomography (CT) scan images. This research mainly focused on segmenting liver and tumor from the abdominal CT scan images using a deep learning method and minimizing the effort and time used for a liver cancer diagnosis. The algorithm is based on the original UNet architecture. But, here in this paper, the numbers of filters on each convolutional block were reduced and new batch normalization and a dropout layer were added after each convolutional block of the contracting path. Results Using this algorithm a dice score of 0.96, 0.74, and 0.63 were obtained for liver segmentation, segmentation of tumors from the liver, and the segmentation of tumor from abdominal CT scan images respectively. The segmentation results of liver and tumor from the liver showed an improvement of 0.01 and 0.11 respectively from other works. Conclusion This work proposed a liver and a tumor segmentation method using a UNet architecture as a baseline. Modification regarding the number of filters and network layers were done on the original UNet model to reduce the network complexity and improve segmentation performance. A new class balancing method is also introduced to minimize the class imbalance problem. Through these, the algorithm attained better segmentation results and showed good improvement. However, it faced difficulty in segmenting small and irregular tumors.

scholarly journals Deep Learning Based Liver Cancer Segmentation from Computed Tomography Images

2020 ◽  
Author(s):  
Yodit Abebe Ayalew ◽  
Kinde Anlay Fante ◽  
Mohammed Aliy
Keyword(s):  
Computed Tomography ◽  
Deep Learning ◽  
Liver Cancer ◽  
Ct Scan ◽  
Tumor Segmentation ◽  
Cancer Death ◽  
Liver Segmentation ◽  
Abdominal Ct ◽  
Computed Tomography Images ◽  
Abdominal Ct Scan

Abstract Background: Liver cancer is the sixth most common cancer worldwide. According to WHO data in 2017, the liver cancer death in Ethiopia reached 1040 (0.16%) from all cancer deaths. Hepatocellular carcinoma (HCC), primary liver cancer causes the death of around 700,000 people each year worldwide and this makes it the third leading cause of cancer death. HCC is occurred due to cirrhosis and hepatitis B or C viruses. Liver cancer mostly diagnosed with a computed tomography (CT) scan. But, the detection of the tumor from the CT scan image is difficult since tumors have similar intensity with nearby tissues and may have a different appearance depending on their type, state, and equipment setting. Nowadays deep learning methods have been used for the segmentation of liver and its tumor from the CT scan images and they are more efficient than those traditional methods. But, they are computationally expensive and need many labeled samples for training, which are difficult in the case of biomedical images. Results: A deep learning-based segmentation algorithm is employed for liver and tumor segmentation from abdominal CT scan images. Three separate UNet models, one for liver segmentation and the others two for tumor segmentation from the segmented liver and directly from the abdominal CT scan image were used. A dice score of 0.96 was obtained for liver segmentation. And a dice score of 0.74 and 0.63 was obtained for segmentation of tumor from the liver and from abdominal CT scan image respectively. Conclusion: The research improves the liver tumor segmentation that will help the physicians in the diagnosis and detection of liver tumors and in designing a treatment plan for the patient. And for the patient, it increases the patients’ chance of getting treatment and decrease the mortality rate due to liver cancer.

scholarly journals Significance of Gastric Wall Thickening Detected in Abdominal CT Scan to Predict Gastric Malignancy

2019 ◽  
Vol 2019 ◽  
pp. 1-6
Author(s):  
A. Akbas ◽  
H. Bakir ◽  
M. F. Dasiran ◽  
H. Dagmura ◽  
Z. Ozmen ◽  
...  
Keyword(s):  
Computed Tomography ◽  
Ct Scan ◽  
Wall Thickness ◽  
Gastric Wall ◽  
Hemoglobin Level ◽  
Wall Thickening ◽  
Endoscopic Evaluation ◽  
Abdominal Ct ◽  
Abdominal Ct Scan ◽  
Gastric Malignancy

Background. Early diagnosis of gastric cancer is one of the most important parameters affecting the survival of the disease. In this study, we aimed to stress the importance of antrum wall thickness in CT examination. Method. The study included 111 patients between ages of 18 and 95 who had antral wall thickening in computed tomography and also had endoscopic evaluation performed in the same clinic. The patients were divided into two groups as benign and malignant according to the pathology results. The thickness of the antrum wall in computed tomography, hemoglobin and albumin levels, and age was compared among these two groups. Parameters with significant differences were further analyzed by multivariate analysis using logistic regression analysis. Results. Of the 111 patients included in the study, 57 were male and 54 were female. Mean age was 65 years. Fifty-one patients were classified as benign and 60 patients as malignant. Mean age of the malignant patients was 70, while that of benign patients was 59 (p<0.05). Antrum wall thickness was 13.68 ± 3.27 mm in malignant patients and 9.22 ± 2.17 mm in benign patients (p<0.05). Similarly, hemoglobin level was significantly different in malignant and benign patients (10.78 ± 1.57 g/dl and 12.64 ± 1.43 g/dl, respectively; p<0.05). Albumin levels were 3.36 ± 0.57 mg/dl in malignant patients and 3.97 ± 0.57 mg/dl in benign patients (p<0.05). Conclusion. Evaluation of antrum wall thickness, age, hemoglobin, and albumin values together may contribute to distinguishing the benign and malignant pathologies involving this region in patients with suspected stomach wall thickening in abdominal CT scan.

Preoperative Abdominal Computed Tomography at Rest and During Valsalva’s Maneuver to Evaluate Incisional Hernias

2019 ◽  
Vol 26 (5) ◽  
pp. 519-527 ◽  
Author(s):  
Gabriele Bellio ◽  
Tommaso Cipolat Mis ◽  
Roberto Del Giudice ◽  
Gabriele Munegato
Keyword(s):  
Computed Tomography ◽  
Ct Scan ◽  
Cohort Analysis ◽  
Binary Logistic Regression ◽  
Binary Logistic Regression Analysis ◽  
Abdominal Ct ◽  
Incisional Hernias ◽  
Abdominal Computed Tomography ◽  
Abdominal Ct Scan ◽  
Valsalva’S Maneuver

Background. Incisional hernias (IHs) can develop in up to 15% of patients who underwent an abdominal surgical procedure. Abdominal computed tomography (CT) is the best examination to evaluate these patients before surgical repair. The aim of this study is to assess the usefulness of the abdominal CT scan during Valsalva’s maneuver in patients who are candidates for surgery. Methods. A retrospective cohort analysis conducted on prospectively recorded data was performed on 26 consecutive patients affected by IHs who underwent a preoperative abdominal CT scan both at rest and during Valsalva’s maneuver between January 1, 2015, and December 31, 2016. Results. Five patients (19%) had IH classified as M1-M2, 10 (39%) as M3, and 11 (42%) as M4-M5. Both the median IH orifice area (IHOA) and the median volume of the IH increased during straining ( P = .001 and P < .001, respectively). The percentage of the difference in volume ratios increased as the localization of the IH moved caudally. At the binary logistic regression analysis M3 IH, body mass index >28, IHOA > 156 cm2 at rest, and IHOA > 138 cm2 during Valsalva’s maneuver were risk factors for posterior component separation. Conclusions. The preoperative CT scan both at rest and during Valsalva’s maneuver seemed useful to estimate the risk of difficult IH repairs. Moreover, it could allow surgeons to decide if the patient should be addressed to more specialized centers.

TRAUMA GINJAL

2020 ◽  
Vol 4 (1) ◽  
pp. 52-57
Author(s):  
Noflih Sulistia ◽  
Bambang Soeprijanto ◽  
Indrastuti Normahayu ◽  
Lenny Violetta
Keyword(s):  
Ct Scan ◽  
Pediatric Patients ◽  
Radiological Examination ◽  
Renal Trauma ◽  
Abdominal Ct ◽  
Abdominal Ct Scan

Renal trauma in children is more common than in adults. Clinically in pediatric patients with renal trauma do not always describe the degreeof trauma. Radiological examination, especially abdominal CT-scan with contrast, can help evaluate the damage to the kidneys so that it candetermine the degree of trauma.

Study on the Radiation Dose of Abdominal CT Scan Using Dual Energy

2018 ◽  
Vol 20 (2) ◽  
pp. 123-132
Author(s):  
Dae-hyun Park ◽  
Young-Kyoon Kim ◽  
Jong-Ho Ahn ◽  
Kwang-Hyun Chang ◽  
Yoon-Chul Nam ◽  
...  
Keyword(s):  
Radiation Dose ◽  
Ct Scan ◽  
Dual Energy ◽  
Abdominal Ct ◽  
Abdominal Ct Scan

scholarly journals Splenic abscess caused by Streptococcus anginosus bacteremia secondary to urinary tract infection: a case report and literature review

Open Medicine ◽  
2020 ◽  
Vol 15 (1) ◽  
pp. 997-1002
Author(s):  
Hao Wu ◽  
Rui Zheng
Keyword(s):  
Urinary Tract Infection ◽  
Urinary Tract ◽  
Tract Infection ◽  
Ct Scan ◽  
Splenic Abscess ◽  
Low Density ◽  
Abdominal Ct ◽  
Streptococcus Anginosus ◽  
Abdominal Ct Scan ◽  
Tract Infections

AbstractOrgan abscesses caused by Streptococcus anginosus are relatively rare. We report the case of an elderly woman with splenic abscess caused by S. anginosus bacteremia after urinary tract infection. An 82-year-old woman had a history of frequency of urination, urgency, and fever with chills for over 10 days prior to admission. An abdominal computed tomography (CT) scan performed in the emergency room revealed a low-density lesion in the spleen, kidney cysts, some exudation around the kidney, and cystitis should be valued. She was treated with ceftriaxone and imipenem/cilastatin. After admission, the blood culture yielded positive results for S. anginosus. A contrast-enhanced abdominal CT scan showed that the low-density lesion previously found in the spleen was smaller than before. After percutaneous drainage of the splenic abscess and treatment with piperacillin/tazobactam based on the antibiotic sensitivity pattern, repeated abdominal CT scan revealed a significant reduction in the low-density lesion. The patient was discharged without recurrence or complications. A systematic review of organ abscess caused by S. anginosus bacteremia was performed. To our knowledge, there has been no report of splenic abscess caused by S. anginosus bacteremia secondary to urinary system tract infection, although urinary tract infections are also an important source.

scholarly journals Small intestine duplication cyst with recurrent hematochezia: a case report and literature review

2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Zhicheng Zhang ◽  
Xiaowei Huang ◽  
Qian Chen ◽  
Demin Li ◽  
Qi Zhou ◽  
...  
Keyword(s):  
Small Intestine ◽  
Case Report ◽  
Literature Review ◽  
Ct Scan ◽  
Duplication Cyst ◽  
Abdominal Ct ◽  
Case Presentation ◽  
Abdominal Ct Scan ◽  
Capsule Endoscopes

Abstract Background Small intestine duplication cysts (SIDCs) are rare congenital anatomical abnormalities of the digestive tract and a rare cause of hematochezia. Case presentation We describe an adult female presented with recurrent hematochezia. The routine gastric endoscope and colonic endoscope showed no positive findings. Abdominal CT scan indicated intussusception due to the "doughnut" sign, but the patient had no typical symptoms. Two subsequent capsule endoscopes revealed a protruding lesion with bleeding in the distal ileum. Surgical resection was performed and revealed a case of SIDC measuring 6 * 2 cm located inside the ileum cavity. The patient remained symptom-free throughout a 7-year follow-up period. Conclusion SIDCs located inside the enteric cavity can easily be misdiagnosed as intussusception by routine radiologic examinations.

Sign in / Sign up

Export Citation Format

Share Document