RESUMEN

Breast ultrasound (BUS) image classification in benign and malignant classes is often based on pre-trained convolutional neural networks (CNNs) to cope with small-sized training data. Nevertheless, BUS images are single-channel gray-level images, whereas pre-trained CNNs learned from color images with red, green, and blue (RGB) components. Thus, a gray-to-color conversion method is applied to fit the BUS image to the CNN's input layer size. This paper evaluates 13 gray-to-color conversion methods proposed in the literature that follow three strategies: replicating the gray-level image to all RGB channels, decomposing the image to enhance inherent information like the lesion's texture and morphology, and learning a matching layer. Besides, we introduce an image decomposition method based on the lesion's structural information to describe its inner and outer complexity. These gray-to-color conversion methods are evaluated under the same experimental framework using a pre-trained CNN architecture named ResNet-18 and a BUS dataset with more than 3000 images. In addition, the Matthews correlation coefficient (MCC), sensitivity (SEN), and specificity (SPE) measure the classification performance. The experimental results show that decomposition methods outperform replication and learning-based methods when using information from the lesion's binary mask (obtained from a segmentation method), reaching an MCC value greater than 0.70 and specificity up to 0.92, although the sensitivity is about 0.80. On the other hand, regarding the proposed method, the trade-off between sensitivity and specificity is better balanced, obtaining about 0.88 for both indices and an MCC of 0.73. This study contributes to the objective assessment of different gray-to-color conversion approaches in classifying breast lesions, revealing that mask-based decomposition methods improve classification performance. Besides, the proposed method based on structural information improves the sensitivity, obtaining more reliable classification results on malignant cases and potentially benefiting clinical practice.

Asunto(s)

RESUMEN

Indolent NK-cell lymphoproliferative disorder of the gastrointestinal tract is a new provisional entity listed in the structure of the forthcoming fifth edition of the World Health Organization (WHO) Classification of Hematolymphoid Tumors. It was first named as "NK-cell enteropathy" and "Lymphomatoid gastropathy" by two independent series a decade ago. Molecular or cytogenetic studies have lent support to the clonal/neoplastic nature of this entity. Herein we add two of such cases that still challenge pathologists and were previously diagnosed as aggressive lymphomas of NK/T derivation.

Asunto(s)

RESUMEN

Objectives: Odontogenic tumors occupy an important position among head and neck tumors. Although, rarely encountered in medical practice but they considered increasingly challenging lesions for the clinicians due to their overlapping clinical and histopathological features. This study was designed to determine the relative frequency of central odontogenic tumors in an Iraqi population by utilizing 2022 WHO tumor classification. Material and methods: Sixty cases of central odontogenic tumors from a total of 1869 case records were retrieved retrospectively from the file archive of the histopathology laboratory in Baghdad medical city from the period of 2016 to 2021. For each individual case, data regarding age, gender, location, and tumor type were collected and analyzed. Results: odontogenic tumors constituted 3.2% of the total cases analyzed mostly benign. The male to female ratio was 1/1. The age of the patients ranged from 11 to 75 years. Most cases were recorded in the third and fourth decades of life (n=31, 51.6%). The most common benign and malignant tumors were ameloblastoma and ameloblastic fibrosarcoma respectively. Most of these tumors located in the mandible (n= 45, 75%). The most common mandibular tumor was ameloblastoma followed by ameloblastic fibroma, and odontogenic myxoma. Regarding maxillary tumors, the predominant tumor was ameloblastoma followed by ameloblastic fibroma, ameloblastic fibrosarcoma, and clear cell odontogenic carcinoma. Conclusions: Odontogenic tumors in an Iraqi population occurred more commonly in the mandible and showed no sex predilection. Most cases were diagnosed in third and fourth decades of life and ameloblastoma was the most frequent odontogenic tumor. The relative frequency of malignant odontogenic tumors was 11.67% of all cases studied mostly ameloblastic fibrosarcoma. (AU)

Objetivos: Os tumores odontogênicos ocupam uma posição importante entre os tumores de cabeça e pescoço. Embora raramente encontrados na prática médica, eles consideram lesões cada vez mais desafiadoras para os clínicos devido às suas características clínicas e histopatológicas sobrepostas. Este estudo foi desenhado para determinar a frequência relativa de tumores odontogênicos centrais em uma população iraquiana, utilizando a classificação de tumor da OMS de 2022. Materiais e métodos: Sessenta casos de tumores odontogênicos centrais de um total de 1.869 registros de casos foram recuperados retrospectivamente do arquivo do laboratório de histopatologia na cidade médica de Bagdá no período de 2016 a 2021. Para cada caso individual, dados sobre idade, sexo , localização e tipo de tumor foram coletados e analisados. Resultados: os tumores odontogênicos constituíram 3,2% do total de casos analisados em sua maioria benignos. A proporção entre homens e mulheres era de 1/1. A idade dos pacientes variou de 11 a 75 anos. A maioria dos casos foi registrada na terceira e quarta décadas de vida (n=31, 51,6%). Os tumores benignos e malignos mais comuns foram ameloblastoma e fibrossarcoma ameloblástico, respectivamente. A maioria desses tumores localizava-se na mandíbula (n= 45, 75%). O tumor mandibular mais comum foi o ameloblastoma, seguido do fibroma ameloblástico e do mixoma odontogênico. Em relação aos tumores maxilares, o tumor predominante foi o ameloblastoma seguido de fibroma ameloblástico, fibrossarcoma ameloblástico e carcinoma odontogênico de células claras. Conclusões: Os tumores odontogênicos em uma população iraquiana ocorreram mais comumente na mandíbula e não mostraram predileção por sexo. A maioria dos casos foi diagnosticada na terceira e quarta décadas de vida, sendo o ameloblastoma o tumor odontogênico mais frequente. A frequência relativa de tumores odontogênicos malignos foi de 11,67% de todos os casos estudados principalmente fibrossarcoma ameloblástico (AU)

Asunto(s)

Asunto(s)

RESUMEN

In vivo proton magnetic resonance spectroscopy (¹H-MRS) is a technique capable of assessing biochemical content and pathways in normal and pathological tissue. In the brain, ¹H-MRS complements the information given by magnetic resonance images. The main goal of the present study was to assess the accuracy of ¹H-MRS for the classification of brain tumors in a pilot study comparing results obtained by manual and semi-automatic quantification of metabolites. In vivo single-voxel ¹H-MRS was performed in 24 control subjects and 26 patients with brain neoplasms that included meningiomas, high-grade neuroglial tumors and pilocytic astrocytomas. Seven metabolite groups (lactate, lipids, N-acetyl-aspartate, glutamate and glutamine group, total creatine, total choline, myo-inositol) were evaluated in all spectra by two methods: a manual one consisting of integration of manually defined peak areas, and the advanced method for accurate, robust and efficient spectral fitting (AMARES), a semi-automatic quantification method implemented in the jMRUI software. Statistical methods included discriminant analysis and the leave-one-out cross-validation method. Both manual and semi-automatic analyses detected differences in metabolite content between tumor groups and controls (P < 0.005). The classification accuracy obtained with the manual method was 75 percent for high-grade neuroglial tumors, 55 percent for meningiomas and 56 percent for pilocytic astrocytomas, while for the semi-automatic method it was 78, 70, and 98 percent, respectively. Both methods classified all control subjects correctly. The study demonstrated that ¹H-MRS accurately differentiated normal from tumoral brain tissue and confirmed the superiority of the semi-automatic quantification method.

Asunto(s)