Introduction: IgA nephropathy (IgAN) has a heterogeneous presentation and the progression to end stage renal disease (ESRD) is often influenced by demographics, ethnicity, as well as choice of treatment regimen. In this study, we investigated the long term survival of IgAN patients in our center and the factors affecting it.Methods: This study included all biopsy-proven IgAN patients with ≥ 1year follow-up. Patients with diabetes mellitus at diagnosis and secondary IgAN were excluded. Medical records were reviewed for demographics, clinical presentation, blood pressure, 24-hour urine protein, serum creatinine, renal biopsy and treatment received. The primary outcome was defined as combined event of 50% estimated glomerular filtration rate (eGFR) reduction or ESRD.Results: We included 130 (74 females; 56 males) patients of mean age 38.0 ± 14.0 years and median eGFR of 75.2 (interquartile range (IQR) 49.3–101.4) ml/min/1.73m². Eighty-four (64.6%) were hypertensive at presentation, 35 (26.9%) had nephrotic syndrome and 57 (43.8%) had nephrotic range proteinuria (NRP). Median follow-up duration was 7.5 (IQR 4.0–13.0) years. It was noted that 18 (13.8%) developed ESRD and 34 (26.2%) reached the primary outcome. Annual eGFR decline was -2.1 (IQR -5.3 to -0.1) ml/min/1.73m2/year, with median survival of 20 years. Survival rates from the combined event (50% decrease in eGFR or ESRD) at 10, 20 and 30 years were 80%, 53% and 25%, while survival from ESRD were 87%, 73% and 65%, respectively. In the univariate analysis, time-average proteinuria (hazard ratio (HR) = 2.41, 95% CI 1.77–3.30), eGFR <45ml/min/1.73m2 at biopsy (HR = 2.35, 95% CI 1.03–5.32), hypertension (HR = 2.81, 95% CI 1.16–6.80), mean arterial pressure (HR = 1.02, 95% CI 1.01–1.04), tubular atrophy/interstitial fibrosis score (HR = 3.77, 95% CI 1.84–7.73), and cellular/fibrocellular crescent score (HR = 2.44, 95% CI 1.19–5.00) were found to be significant. Whereas only time-average proteinuria (TA-proteinuria) remained as a significant predictor in the multivariate analysis (HR = 2.23, 95% CI 1.57–3.16).Conclusion: In our cohort, TA-proteinuria was the most important predictor in the progression of IgAN, irrespective of degree of proteinuria at presentation.

This chapter discusses radio-pathological correlation with recent imaging advances such as machine learning (ML) with the use of technical methods such as mammography and histopathology. Although criteria for diagnostic categories for radiology and pathology are well established, manual detection and grading, respectively, are tedious and subjective processes and thus suffer from inter-observer and intra-observer variations. Two most popular techniques that use ML, computer aided detection (CADe) and computer aided diagnosis (CADx), are presented. CADe is a rejection model based on SVM algorithm which is used to reduce the False Positive (FP) of the output of the Chan-Vese segmentation algorithm that was initialized by the marker controller watershed (MCWS) algorithm. CADx method applies the ensemble framework, consisting of four-base SVM (RBF) classifiers, where each base classifier is a specialist and is trained to use the selected features of a particular tissue component. In general, both proposed methods offer alternative decision-making ability and are able to assist the medical expert in giving second opinion on more precise nodule detection. Hence, it reduces FP rate that causes over segmentation and improves the performance for detection and diagnosis of the breast cancer and is able to create a platform that integrates diagnostic reporting system.

Thyroid carcinoma showing thymic-like differentiation (CASTLE) is a rare malignancy of the thyroid gland, and it accounts for 0.1–0.15% of all thyroid cancers. As the name suggests, it has a histological and immunophenotypic resemblance to thymic carcinoma. Preoperative diagnosis of CASTLE can be difficult as its clinical manifestations, and histological characteristic resembles other aggressive and advanced thyroid carcinomas. It is essential to distinguish CASTLE from other aggressive neoplasms as the former has a more favourable prognosis. Immunohistochemical staining with CD5 can help to differentiate thyroid CASTLE from other aggressive thyroid neoplasms. Due to the rarity of this disease, there is no clear definitive treatment strategy. Surgical resection of CASTLE is usually attempted initially. Nodal involvement and extrathyroidal extension are shown to be the main prognostic factors that influenced the survival of patients. Therefore, complete resection of the tumour is vital to reduce local recurrence rates and to improve the chance of long-term survival. Radiotherapy (RT) for CASTLE is an effective treatment. Curative surgery followed by adjuvant RT should be considered in cases with extrathyroidal extension and nodal metastases. With RT, shrinkage of the tumour and reduction of local recurrence rate is possible. With that in mind, we present a case of CASTLE who presented with airway compression symptoms three years after thyroid surgery. He subsequently underwent tumour debulking surgery and a tracheostomy. The patient refused adjuvant chemoradiotherapy, and during our serial follow-up, he is well and symptom-free.

Prostate cancer diagnosis is based mainly by microscopic evaluation of prostate tissue biopsy which includes assigning cancer grading. The latter is crucial in evaluating the prognosis or cancer progression and treatment. The common grading system used is Gleason grading system that classifies the prostate cancer into five basic grades based on the architecture and pattern of glandular proliferation. However, this process may be subjected to inter and intra observer variation. Therefore, the main aim of this paper is to develop a computer aided diagnosis (CAD) utilizing supervised machine learning techniques for Gleason grading of prostate histology. The proposed procedure utilizes the main tissue components of the images in an ensemble style to correctly classify the input histopathological image into benign or malignant. Moreover, the texture features of the benign and malignant images can be used to build the proposed ensemble framework. However, not all extracted texture features contribute to the improvement of the classification performance of the proposed ensemble framework. Therefore, to select the more informative features from a set is a critical issue. In this study, a new multi-scoring features selection method based on SVM-RFE and conditional mutual information (CMI) is proposed.