Computer-assisted mitotic count using a deep learning–based algorithm improves interobserver reproducibility and accuracy

The mitotic count (MC) is an important histological parameter for prognostication of malignant neoplasms. However, it has inter- and intraobserver discrepancies due to difficulties in selecting the region of interest (MC-ROI) and in identifying or classifying mitotic figures (MFs). Recent progress in the field of artificial intelligence has allowed the development of high-performance algorithms that may improve standardization of the MC. As algorithmic predictions are not flawless, computer-assisted review by pathologists may ensure reliability. In the present study, we compared partial (MC-ROI preselection) and full (additional visualization of MF candidates and display of algorithmic confidence values) computer-assisted MC analysis to the routine (unaided) MC analysis by 23 pathologists for whole-slide images of 50 canine cutaneous mast cell tumors (ccMCTs). Algorithmic predictions aimed to assist pathologists in detecting mitotic hotspot locations, reducing omission of MFs, and improving classification against imposters. The interobserver consistency for the MC significantly increased with computer assistance (interobserver correlation coefficient, ICC = 0.92) compared to the unaided approach (ICC = 0.70). Classification into prognostic stratifications had a higher accuracy with computer assistance. The algorithmically preselected hotspot MC-ROIs had a consistently higher MCs than the manually selected MC-ROIs. Compared to a ground truth (developed with immunohistochemistry for phosphohistone H3), pathologist performance in detecting individual MF was augmented when using computer assistance (F1-score of 0.68 increased to 0.79) with a reduction in false negatives by 38%. The results of this study demonstrate that computer assistance may lead to more reproducible and accurate MCs in ccMCTs.

A Genetic-Fuzzy System Algorithm Method for the Breast Cancer Diagnosis Problem

Breast cancer is an important medical problem, especially for women, computer-aided medical diagnosis is very important in terms of prevention and early detection. This paper presents early detection of breast cancer using two methods, namely genetic algorithm and fuzzy inference system which will be used for early detection of breast cancer which will be used by doctors with computer assistance to obtain medical diagnosis of breast cancer in Indonesia. Our research shows that the diagnosis of breast cancer using these two methods has a high level of accuracy.

Kekuatan Lengan dan Keseimbangan Terhadap Kemampuan Handstand Atlet Daradaeng Gymnastic Club

This study aims to determine the relationship between arm strength and balance on handstand ability. This research is descriptive with two independent variables, namely arm strength and balance with one dependent variable, namely handstand ability. The sample of this research is the athletes of the Makassar Daradaeng Gymnastics Club as many as 20 people. The data analysis technique used is descriptive analysis, correlation coefficient analysis at a significant level of 0.05, using computer assistance through the SPSS program. The results showed: (1) There was a significant contribution between arm strength and Handstand ability, namely Daradaeng Gymanstic Club Makassar athlete with an R Squares value of 0.758 (2) There was a significant contribution between balance and Handstand ability of Daradaeng Gymanstic Club Makassar athlete with an R value. Squares of 0.758 (3) There is a significant contribution between arm strength and balance together with the Handstand ability of Physical Education students with a value (R) of 0.852 and an Fcount (F) of 48.816

AN EXPLORATION OF NABHI AS AN ANATOMICAL LANDMARK IN AYURVEDA

Ayurveda is a scientific text which covers all aspects of Rachana Sharir and Kriya Sharir. This Sharir is now-a-days modernized as Anatomy and Physiology. To understand anatomy the primary knowledge of anatomical landmarks is essential. Reference points located by visual inspection, palpation, or computer assistance are useful in localizing structures on or within the human body are called Anatomical landmarks. These are frequently used by Anatomists and clinicians to guide both diagnosis and treatment. In Ayurveda, the concept of Anatomical landmark is already present but in scattered manner. The concept of Nabhi in Ayurveda is many folded concept which needs more exploration. It can be considered as Koshthanga, as Marma, as Sira & Dhamani Prabhava Sthana, as an anatomical landmark and many more. In this paper an attempt has been made to collect references related to Nabhi from various Samhitas indicating it as an anatomical landmark and by analyzing these references logically, the concept of Nabhi as an important landmark has been established and reconstructed in accordance with modern Anatomical landmark categories.

PENGARUH TERAPI MADU TERHADAP PENURUNAN FREKUENSI BUANG AIR BESAR PADA ANAK USIA 0-2 TAHUN YANG MENGALAMI DIARE DI RUMAH SAKIT UMUM DAERAH DELI SERDANG LUBUK PAKAM TAHUN 2020

Diarrhea is a disease characterized by changes in the shape and consistency of stools were soft until melted and increased frequency of bowel movements than usual, which is 3 times or more a day which may be accompanied by vomiting or bloody stools. Diarrheal disease is still a global problem with the degree of morbidity and mortality are high in many countries, especially in developing countries and as one of the major causes of morbidity and mortality of children in the world. From laboratory studies and clinical trials, pure honey has bactericidal activity against several organisms that can entropathogenic, including species of Salmonella, Shigella, and E. coli. The goal of this research was to determine the effect of honey therapy to decrease the frequency of bowel movements in children aged 0-2 years who had diarrhea in district general hospitals deli serdang Lubuk pakam 2020. This research was conducted by quasi experimental research design through the design time series design , The sample in this study using the technique of sampling purvosive the number of 10 people as respondent data obtained using observation sheets and tested by t-test (paired sample t-test) and computer assistance. From the results of research conducted on 10 respondents obtained results p <α (0.005 <0.05), which describes the influence of honey therapy to decrease the frequency of bowel movements in children aged 0-2 years who had diarrhea in hospital common areas serdang deli depths Pakam. Thus Ho is rejected and Ha accepted.

The Remote Analysis of Breath Sound in COVID-19 Patients: A Series of Clinical cases (Preprint)

BACKGROUND Respiratory sounds have been recognized as a possible indicator of behavior and health. Computer analysis of these sounds can indicate of characteristic sound changes caused by COVID-19 and can be used for diagnosis of this illness OBJECTIVE The communication aim is development of fast remote computer-assistance diagnosis methods for COVID-19, based on analysis of respiratory sounds METHODS Fast Fourier transform (FFT) was applied for computer analysis of respiratory sounds recorded near the mouth of 14 COVID-19 patients (age 18-80) and 17 healthy volunteers (age from 5 to 48). Sampling rate was from 44 to 96 kHz. Unlike usual computer-assistance methods of diagnostics of illness, based on respiratory sound analysis, we propose to test the high frequency part of the FFT spectrum (2000-6000 Hz). RESULTS Comparing FFT spectrums of the respiratory sounds of the patients and volunteers we developed computer-assistance methods of COVID 19 diagnostics and determined numerical healthy-ill criterions. These criterions are independent of gender and age of the tested person. CONCLUSIONS The proposed computer methods, based on analysis of the FFT spectrums of respiratory sounds of the patients and volunteers, allows one to automatically diagnose COVID-19 with sufficiently high diagnostic values. These methods can be applied to develop noninvasive self-testing kits for COVID-19.

Computer-Assisted Mitotic Count Using a Deep Learning-based Algorithm Improves Inter-Observer Reproducibility and Accuracy in canine cutaneous mast cell tumors

The mitotic count (MC) is an important histological parameter for prognostication of malignant neoplasms. However, it has inter- and intra-observer discrepancies due to difficulties in selecting the region of interest (MC-ROI) and in identifying/classifying mitotic figures (MFs). Recent progress in the field of artificial intelligence has allowed the development of high-performance algorithms that may improve standardization of the MC. As algorithmic predictions are not flawless, the computer-assisted review by pathologists may ensure reliability. In the present study we have compared partial (MC-ROI preselection) and full (additional visualization of MF candidate proposal and display of algorithmic confidence values) computer-assisted MC analysis to the routine (unaided) MC analysis by 23 pathologists for whole slide images of 50 canine cutaneous mast cell tumors (ccMCTs). Algorithmic predictions aimed to assist pathologists in detecting mitotic hotspot locations, reducing omission of MF and improving classification against imposters. The inter-observer consistency for the MC significantly increased with computer assistance (interobserver correlation coefficient, ICC = 0.92) compared to the unaided approach (ICC = 0.70). Classification into prognostic stratifications had a higher accuracy with computer assistance. The algorithmically preselected MC-ROIs had a consistently higher MCs than the manually selected MC-ROIs. Compared to a ground truth (developed with immunohistochemistry for phosphohistone H3), pathologist performance in detecting individual MF was augmented when using computer assistance (F1-score of 0.68 increased to 0.79) with a reduction in false negatives by 38%. The results of this study prove that computer assistance may lead to a more reproducible and accurate MCs in ccMCTs.