Breast cancer is the most commonly diagnosed cancer among women, globally. The occurrence and fatality rates are high for breast cancer compared to other types of cancer. The World Cancer report 2020 points out early detection and rapid treatment as the most efficient intervention to control this malignancy. Histopathological image analysis has great significance in early diagnosis of the disease. Our work has significant biological and medical potential for automatically processing different histopathology images to identify breast cancer and its corresponding grade. Unlike the existing models, we grade breast cancer by including both local and global features. The proposed model is a hybrid multi-class classification model using depth-wise separable convolutional networks and transformers, where both local and global features are considered. In order to resolve the self-attention module complexity in transformers patch merging is performed. The proposed model can classify pathological images of public breast cancer data sets into different categories. The model was evaluated on three publicly available datasets, like BACH, BreakHis and IDC. The accuracy of the proposed model is 97.800 % on the BACH dataset, 98.130 % on BreakHis dataset and 98.320 % for the IDC dataset.

Background: Chemo-radiotherapy has become the standard of care for loco-regionally advanced head and neck cancers. Platinum based regimens are the most effective. Although benefits are proven with chemo-radiation, acute toxicities are markedly increased. The dose and delivery schedules of Cisplatin have ranged from intermittent higher dose [100 mg/m2] every 3 weeks to low dose [6 mg/m2] daily administration. At present there is no data indicating which regimen is superior. Purpose: To compare acute toxicities of two chemotherapy schedules for head and neck cancers. Materials and Methods: A total of 83 head and neck cancer patients treated with two schedules of concurrent chemo RT were analyzed, retrospectively, for treatment toxicity. In group A [51 patients], chemotherapy [CT] was administered on week 1, 4 and 7 [cisplatin 100 mg/m2] over a period of 2-3 days. In group B [32 patients], CT was delivered weekly [cisplatin 40 mg/m2]. Radiotherapy dose was 7000 cGy in 35 fractions for definitive concurrent chemo-radiation and 6600 cGy in 33 fractions for adjuvant treatment. Results: Group B patients had increased grade III skin and hematological toxicity, where as patients in group A had more pharyngeal toxicity. Treatment interruptions and percentage of weight loss were higher in group B. Weekly CT schedule had higher rate of severe mucositis, which was statistically significant on both univariate [ P =0.005] and multivariate [ P =0.007] analysis. Conclusions: Three weekly CT is less toxic than weekly. Weekly CT can be made more acceptable by reducing the dose and using feeding tubes for nutrition.

Sister Joseph nodule is a metastatic umbilical lesion secondary to a primary malignancy of any viscera. It can be a presenting symptom (a sign of undiagnosed malignancy) or a symptom or sign of progression or recurrence in a known case. Its incidence is 1–3% of all intra-abdominal or pelvic malignancies. Here, we present 4 such cases, with Sister Joseph nodule as a finding of (1) presentation in a case of gallbladder carcinoma, (2) progression in a case of malignant gastrointestinal stromal tumour, (3) recurrence in a case of ovarian carcinoma, and (4) presentation in a case of rectal carcinoma. The clinicopathologic features of all 4 patients are discussed, and the related literature is briefly reviewed.