Machine Learning in the Differentiation of Soft Tissue Neoplasms: Comparison of Fat-Suppressed T2WI and Apparent Diffusion Coefficient (ADC) Features-Based Models

Machine learning has been widely used in the characterization of tumors recently. This article aims to explore the feasibility of the whole tumor fat-suppressed (FS) T2WI and ADC features-based least absolute shrinkage and selection operator (LASSO)-logistic predictive models in the differentiation of soft tissue neoplasms (STN). The clinical and MR findings of 160 cases with 161 histologically proven STN were reviewed, retrospectively, 75 with diffusion-weighted imaging (DWI with b values of 50, 400, and 800 s/mm2). They were divided into benign and malignant groups and further divided into training (70%) and validation (30%) cohorts. The MR FS T2WI and ADC features-based LASSO-logistic models were built and compared. The AUC of the FS T2WI features-based LASSO-logistic regression model for benign and malignant prediction was 0.65 and 0.75 for the training and validation cohorts. The model’s sensitivity, specificity, and accuracy of the validation cohort were 55%, 96%, and 76.6%. While the AUC of the ADC features-based model was 0.932 and 0.955 for the training and validation cohorts. The model’s sensitivity, specificity, and accuracy were 83.3%, 100%, and 91.7%. The performances of these models were also validated by decision curve analysis (DCA). The AUC of the whole tumor ADC features-based LASSO-logistic regression predictive model was larger than that of FS T2WI features (p = 0.017). The whole tumor fat-suppressed T2WI and ADC features-based LASSO-logistic predictive models both can serve as useful tools in the differentiation of STN. ADC features-based LASSO-logistic regression predictive model did better than that of FS T2WI features.

Aggressive Embryonal Orbital Rhabdomyosarcoma in an Adolescent

Rhabdomyosarcoma is a highly malignant neoplasm originating mainly from undifferentiated mesenchymal tissue. It is one of the commonest soft tissue neoplasms in the head and neck region, with an incidence of 4.3 cases per million.1 Approximately 10 % of the cases reported occur in the orbit. It is considered a disease of young children with strong male prevalence.2 This article presents a case of a 12- year-old girl with embryonal orbital rhabdomyosarcoma which is a rare occurrence among adolescents and its management challenges.

The many faces of solitary fibrous tumor; diversity of histological features, differential diagnosis and role of molecular studies and surrogate markers in avoiding misdiagnosis and predicting the behavior

Background Solitary Fibrous Tumor (SFT) is a distinct soft tissue neoplasm associated with NAB2-STAT6 gene fusion. It can involve a number of anatomic sites and exhibits a wide spectrum of histological features. Main body Apart from diversity in morphological features seen even in conventional SFT, two histologic variants (fat-forming and giant cell-rich) are also recognized. In addition, a malignant form and dedifferentiation are well recognized. Owing to diverse histological features and involvement of diverse anatomic locations, SFT can mimic other soft tissue neoplasms of different lineages including schwannoma, spindle cell lipoma, dermatofibrosarcoma protuberans, liposarcoma, gastrointestinal stromal tumor (GIST), malignant peripheral nerve sheath tumor (MPNST), and synovial sarcoma. SFT is classified as an intermediate (rarely metastasizing) tumor according to World Health Organization Classification of Tumors of Soft tissue and Bone, 5th edition. The management and prognosis of SFT differs from its malignant mimics and correct diagnosis is therefore important. Although SFT expresses a distinct immunohistochemical (IHC) profile, the classic histomorphological and IHC profile is not seen in all cases and diagnosis can be challenging. NAB2-STAT6 gene fusion has recently emerged as a sensitive and specific molecular marker and its IHC surrogate marker signal transducer and activator of transcription 6 (STAT6) has also shown significant sensitivity and specificity. However, few recent studies have reported STAT6 expression in other soft tissue neoplasms. Conclusion This review will focus on describing the diversity of histological features of SFT, differential diagnoses and discussing the features helpful in distinguishing SFT from its histological mimics.

Advanced Cutaneous Leiomyosarcoma of the Forearm

Leiomyosarcoma is a malignant smooth muscle neoplasm, which is traditionally divided into superficial and deep tumors. Superficial leiomyosarcomas are quite rare entities, accounting for approximately 7% of soft tissue neoplasms and 0.04% of all cancers. Here we describe a rare case of advanced primary cutaneous leiomyosarcoma (PCL) in a 93-year-old woman, highlighting the considerable size of the lesion and the correct surgical and oncological management. The clinical story began about 4 years ago, and the neoplasia was treated only with local radiotherapy, but the patient suffered from a dramatic volumetric increase of the right arm sarcoma one year ago. Then, an amputation of the limb was performed without following adjuvant chemotherapy. Currently, she does not show signs of recurrence and is in good shape.

Diagnostic Differences in Expert Second-Opinion Consultation Cases at a Tertiary Sarcoma Center

Soft tissue tumors are diagnostically challenging, and it is recommended that these are reported or reviewed by specialist soft tissue pathologists. We present our experience with second-opinion (consultation) cases in a specialist tertiary sarcoma center. The aim of this study was to determine areas of diagnostic difficulty in soft tissue pathology. We assessed 581 second-opinion cases which were reviewed by two experienced pathologists in a period of one year. There was 62% concordance between the original and the second-opinion diagnosis, with diagnostic discrepancy in 38%. The largest group of soft tissue neoplasms received for second opinion was fibroblastic/myofibroblastic tumors, and most major diagnostic problems were encountered in adipocytic and so-called “fibrohistiocytic” tumors. Major diagnostic errors impacting management were found in 148 cases (25%). Morphologic assessment of tumors, judicious use of molecular techniques, newer immunostains and their interpretation, along with importance of knowledge of rarer entities were found to be most useful in avoiding errors.