Enhanced MRI Radiomics Based Model for Predicting Recurrence or Metastasis of Nasopharyngeal Cancer (NC) Undergoing Concurrent Chemoradiotherapy: A Retrospective Study.

Nasopharyngeal Carcinoma (NC) refers to the malignant tumor that occurs at the top and side walls of the nasopharyngeal cavity. The NC incidence rate always dominates the first among the malignant tumors of the ear, nose and throat, and mainly occurs in Asia. NC cases are mainly concentrated in southern provinces in China, with about 4 million existing NC. With the pollution of environment and pickled diet, and the increase of life pressure, the domestic NC incidence rate has reached 4.5-6.5/100000 and is increasing year by year. It was reported that the known main causes of NC include hereditary factor, genetic mutations, and EB virus infection, common clinical symptoms of NC include nasal congestion, bloody mucus, etc. About 90% of NC is highly sensitive to radiotherapy which is regard as the preferred treatment method; However, for NC with lower differentiation, larger volume, and recurrence after treatment, surgical resection and local protons and heavy ions therapy are also indispensable means. According to reports, the subtle heterogeneity and diversity exists in some NC, with about 80% of NC undergone radiotherapy and about 25% experienced recurrence and death within five years after radiotherapy in China. Therefore, screening the NC population with suspected recurrence after concurrent chemoradiotherapy may improve survival rates in current clinical decision-making.

NC is one of the prevalent malignancies of the head and neck region with poor prognosis. The aim of this study is to establish a predictive model for assessing NC prognosis using clinical and MR radiomics data.

An improved attention module based on nnU-Net for segmenting primary central nervous system lymphoma (PCNSL) in MRI images1.

BACKGROUND: Accurate volumetric segmentation of primary central nervous system lymphoma (PCNSL) is essential for assessing and monitoring the tumor before radiotherapy and the treatment planning. The tedious manual segmentation leads to interindividual and intraindividual differences, while existing automatic segmentation methods cause under-segmentation of PCNSL due to the complex and multifaceted nature of the tumor. OBJECTIVE: To address the challenges of small size, diffused distribution, poor inter-layer continuity on the same axis, and tendency for over-segmentation in brain MRI PCNSL segmentation, we propose an improved attention module based on nnUNet for automated segmentation. METHODS: We collected 114 T1 MRI images of patients in the Huashan Hospital, Shanghai. Then randomly split the total of 114 cases into 5 distinct training and test sets for a 5-fold cross-validation. To efficiently and accurately delineate the PCNSL, we proposed an improved attention module based on nnU-Net with 3D convolutions, batch normalization, and residual attention (res-attention) to learn the tumor region information. Additionally, multi-scale dilated convolution kernels with different dilation rates were integrated to broaden the receptive field. We further used attentional feature fusion with 3D convolutions (AFF3D) to fuse the feature maps generated by multi-scale dilated convolution kernels to reduce under-segmentation. RESULTS: Compared to existing methods, our attention module improves the ability to distinguish diffuse and edge enhanced types of tumors; and the broadened receptive field captures tumor features of various scales and shapes more effectively, achieving a 0.9349 Dice Similarity Coefficient (DSC). CONCLUSIONS: Quantitative results demonstrate the effectiveness of the proposed method in segmenting the PCNSL. To our knowledge, this is the first study to introduce attention modules into deep learning for segmenting PCNSL based on brain magnetic resonance imaging (MRI), promoting the localization of PCNSL before radiotherapy.

Transforming breast cancer care: harnessing the power of artificial intelligence and imaging for predicting pathological complete response. a narrative review.

This narrative review explores the transformative potential of Artificial Intelligence (AI) and advanced imaging techniques in predicting Pathological Complete Response (pCR) in Breast Cancer (BC) patients undergoing Neo-Adjuvant Chemotherapy (NACT). Summarizing recent research findings underscores the significant strides made in the accurate assessment of pCR using AI, including deep learning and radiomics. Such AI-driven models offer promise in optimizing clinical decisions, personalizing treatment strategies, and potentially reducing the burden of unnecessary treatments, thereby improving patient outcomes. Furthermore, the review acknowledges the potential of AI to address healthcare disparities in Low- and Middle-Income Countries (LMICs), where accessible and scalable AI solutions may enhance BC management. Collaboration and international efforts are essential to fully unlock the potential of AI in BC care, offering hope for a more equitable and effective approach to treatment worldwide.

The discerning influence of dynamic contrast-enhanced MRI in anticipating molecular subtypes of breast cancer through the artistry of artificial intelligence - a narrative review.

Radio genomics is an exciting new area that uses diagnostic imaging to discover genetic features of diseases. In this review, we carefully examined existing literature to evaluate the role of artificial intelligence (AI) and machine learning (ML) on dynamic contrastenhanced MRI (DCE-MRI) data to distinguish molecular subtypes of breast cancer (BC). Implications to noninvasive assessment of molecular subtype include reduction in procedure risks, tailored treatment approaches, ability to examine entire lesion, follow-up of tumour biology in response to treatment and evaluation of treatment resistance and failure secondary to tumour heterogeneity. Recent studies leverage radiomics and AI on DCE-MRI data for reliable, non-invasive breast cancer subtype classification. This review recognizes the potential of AI to predict the molecular subtypes of breast cancer non-invasively.

Integrating artificial intelligence techniques for advancements in colorectal cancer management: navigating past and predicting future direction.

Artificial Intelligence (AI) in the last few years has emerged as a valuable tool in managing colorectal cancer, revolutionizing its management at different stages. In early detection and diagnosis, AI leverages its prowess in imaging analysis, scrutinizing CT scans, MRI, and colonoscopy views to identify polyps and tumors. This ability enables timely and accurate diagnoses, initiating treatment at earlier stages. AI has helped in personalized treatment planning because of its ability to integrate diverse patient data, including tumor characteristics, medical history, and genetic information. Integrating AI into clinical decision support systems guarantees evidence-based treatment strategy suggestions in multidisciplinary clinical settings, thus improving patient outcomes. This narrative review explores the multifaceted role of AI, spanning early detection of colorectal cancer, personalized treatment planning, polyp detection, lymph node evaluation, cancer staging, robotic colorectal surgery, and training of colorectal surgeons.

The relationship between imaging features, therapeutic response, and overall survival in pediatric diffuse intrinsic pontine glioma.

We aimed to evaluate the relationship between imaging features, therapeutic responses (comparative cross-product and volumetric measurements), and overall survival (OS) in pediatric diffuse intrinsic pontine glioma (DIPG). A total of 134 patients (≤ 18 years) diagnosed with DIPG were included. Univariate and multivariate analyses were performed to evaluate correlations of clinical and imaging features and therapeutic responses with OS. The correlation between cross-product (CP) and volume thresholds in partial response (PR) was evaluated by linear regression. The log-rank test was used to compare OS patients with discordant therapeutic response classifications and those with concordant classifications. In univariate analysis, characteristics related to worse OS included lower Karnofsky, larger extrapontine extension, ring-enhancement, necrosis, non-PR, and increased ring enhancement post-radiotherapy. In the multivariate analysis, Karnofsky, necrosis, extrapontine extension, and therapeutic response can predict OS. A 25% CP reduction (PR) correlated with a 32% volume reduction (R2 = 0.888). Eight patients had discordant therapeutic response classifications according to CP (25%) and volume (32%). This eight patients' median survival time was 13.0 months, significantly higher than that in the non-PR group (8.9 months), in which responses were consistently classified as non-PR based on CP (25%) and volume (32%). We identified correlations between imaging features, therapeutic responses, and OS; this information is crucial for future clinical trials. Tumor volume may represent the DIPG growth pattern more accurately than CP measurement and can be used to evaluate therapeutic response.

Inter- and Intra-Patient Repeatability of Radiomic Features from Multiparametric Whole-Body MRI in Patients with Metastatic Prostate Cancer.

(1) Background: We assessed the test-re-test repeatability of radiomics in metastatic castration-resistant prostate cancer (mCPRC) bone disease on whole-body diffusion-weighted (DWI) and T1-weighted Dixon MRI. (2) Methods: In 10 mCRPC patients, 1.5 T MRI, including DWI and T1-weighted gradient-echo Dixon sequences, was performed twice on the same day. Apparent diffusion coefficient (ADC) and relative fat-fraction-percentage (rFF%) maps were calculated. Per study, up to 10 target bone metastases were manually delineated on DWI and Dixon images. All 106 radiomic features included in the Pyradiomics toolbox were derived for each target volume from the ADC and rFF% maps. To account for inter- and intra-patient measurement repeatability, the log-transformed individual target measurements were fitted to a hierarchical model, represented as a Bayesian network. Repeatability measurements, including the intraclass correlation coefficient (ICC), were derived. Feature ICCs were compared with mean ADC and rFF ICCs. (3) Results: A total of 65 DWI and 47 rFF% targets were analysed. There was no significant bias for any features. Pairwise correlation revealed fifteen ADC and fourteen rFF% feature sub-groups, without specific patterns between feature classes. The median intra-patient ICC was generally higher than the inter-patient ICC. Features that describe extremes in voxel values (minimum, maximum, range, skewness, and kurtosis) showed generally lower ICCs. Several mostly shape-based texture features were identified, which showed high inter- and intra-patient ICCs when compared with the mean ADC or mean rFF%, respectively. (4) Conclusions: Pyradiomics texture features of mCRPC bone metastases varied greatly in inter- and intra-patient repeatability. Several features demonstrated good repeatability, allowing for further exploration as diagnostic parameters in mCRPC bone disease.

Improving Prostate MR Image Quality in Practice - Initial results from the ACR Prostate MR Image Quality Improvement Collaborative.

OBJECTIVE: Variability in prostate MRI quality is an increasingly recognized problem that negatively affects patient care. This report aims to describe the results and key learnings of the first cohort of the ACR Learning Network Prostate MR Image Quality Improvement Collaborative. METHODS: Teams from five organizations in the U.S. were trained on a structured improvement method. After reaching a consensus on image quality and auditing their images using the Prostate Imaging Quality (PI-QUAL) system, teams conducted a current state analysis to identify barriers to obtaining high-quality images. Through plan-do-study-act cycles involving frontline staff, each site designed and tested interventions targeting image quality key drivers. The percentage of exams meeting quality criteria (i.e., PI-QUAL score ≥ 4) was plotted on a run chart, and project progress was reviewed in weekly meetings. At the collaborative level, the goal was to increase the percentage of exams with PI-QUAL ≥ 4 to at least 85%. RESULTS: Across 2380 exams audited, the mean weekly rates of prostate MR exams meeting image quality criteria increased from 67% (range: 60-74%) at baseline to 87% (range: 80-97%) upon program completion. The most commonly employed interventions were MR protocol adjustments, development and implementation of patient preparation instructions, personell training and development of an auditing process mechanism. CONCLUSION: A Learning Network model, where organizations share knowledge and work together toward a common goal, can improve prostate MR image quality at multiple sites simultaneously. The inaugural cohort's key learnings provide a roadmap for improvement on a broader scale.

Diagnostic performance of computed tomography-digital subtraction angiography and conventional magnetic resonance imaging for evaluating the vascularity of osseous spinal tumors.

BACKGROUND AND PURPOSE: Patients with hypervascular spinal tumors may have severe blood loss during tumor resection, which increases the risks of perioperative morbidity and mortality. However, the preoperative evaluation of tumor vascularity may be challenging; moreover, the reliability of the data obtained in conventional preoperative noninvasive imaging is debatable. In this study, we compared conventional magnetic resonance imaging (MRI) and subtraction computed tomography angiography (CTA) in terms of their performance in vascularity evaluation. The catheter digital subtraction angiography (DSA) technique was used as a reference standard. METHODS: This study included 123 consecutive patients with spinal tumor who underwent subtraction CTA, catheter DSA, and subsequent surgery between October 2015 and October 2021. Data regarding qualitative and semiquantitative subtraction CTA parameters and conventional MRI signs were collected for comparison with tumor vascularity graded through catheter DSA. The diagnostic performance of qualitative CTA, quantitative CTA, and conventional MRI in assessing spinal tumor vascularity was analyzed. RESULTS: Qualitative subtraction CTA was the best noninvasive imaging modality in terms of diagnostic performance (area under the receiver operating characteristic curve [AUROC], 0.95). Quantitative CTA was relatively inferior (AUROC, 0.87). MRI results had low reliability (AUROC, 0.51 to 0.59). Intratumoral hemorrhage and prominent foraminal venous plexus were found to be the specific signs for hypervascularity (specificity 93.2%). CONCLUSIONS: Qualitative subtraction CTA offers the highest diagnostic value in evaluating spinal tumor vascularity, compared to quantitative CTA and MRI. Although conventional MRI may not be a reliable approach, certain MRI signs may have high specificity, which may be crucial for assessing spinal tumor vascularity.

The performance of the node reporting and data system 1.0 (Node-RADS) and DWI-MRI in staging patients with cervical carcinoma according to the new FIGO classification (2018).

PURPOSE: To evaluate the diagnostic accuracy of the Node-RADS score and the utility of apparent diffusion coefficient (ADC) values in predicting metastatic lymph nodes (LNs) involvement in cervical cancer (CC) patients using magnetic resonance imaging (MRI). The applicability of the Node RADS score across three readers with different years of experience in pelvic imaging was also assessed. MATERIAL AND METHODS: Among 140 patients, 68 underwent staging MRI, neoadjuvant chemotherapy and radical surgery, forming the study cohort. Node-RADS scores of the main pelvic stations were retrospectively determined to assess LN metastatic likelihood and compared with the histological findings. Mean ADC, relative ADC (rADC), and correct ADC (cADC) values of LNs classified as Node-RADS ≥ 3 were measured and compared with histological reports, considered as gold standard. RESULTS: Sensitivity, specificity, positive and negative predictive values (PPVs and NPVs), and accuracy were calculated for different Node-RADS thresholds. Node RADS ≥ 3 showed a sensitivity of 92.8% and specificity of 72.5%. Node RADS ≥ 4 yielded a sensitivity of 71.4% and specificity of 100%, while Node RADS 5 yielded 42.9% and 100%, respectively. The diagnostic performance of mean ADC, cADC and rADC values from 78 LNs with Node-RADS score ≥ 3 was assessed, with ADC demonstrating the highest area under the curve (AUC 0.820), compared to cADC and rADC values. CONCLUSION: The Node-RADS score provides a standardized LNs assessment, enhancing diagnostic accuracy in CC patients. Its ease of use and high inter-observer concordance support its clinical utility. ADC measurement of LNs shows promise as an additional tool for optimizing patient diagnostic evaluation.

Study of Comparison of Magnetic Resonance Imaging with Surgical and Pathological features in Carcinoma Rectum Patients.

Colorectal cancer is the second-most common cancer in the females and third-most common cancer in males worldwide and it is the second-most common cause of mortality. In India, colorectal cancer is the fifth-most common cancer overall, constituting 6.3%. With the advent of high-resolution magnetic resonance imaging (MRI), it has become the investigation of choice for local staging of rectal cancers as well as in predicting the response to neoadjuvant treatment and streamlining the management. The aims and objectives of this study were to compare the results of MRI with surgicopathological findings in carcinoma (Ca) rectum patients in Indian patients from a tertiary regional Cancer care centre. An observational retrospective study was carried out in the Department of Surgical Oncology Acharya Harihar Regional Cancer Centre, Cuttack, from January 2021 to June 2022. All the patients who were admitted and planned for the definitive surgery for Ca Rectum and Recto sigmoid Ca were included in the study. A total of 68 patients were included, including both upfront and post-neoadjuvant treatment cases. All the patients who received neoadjuvant treatment underwent an MRI for local staging. The findings of MRI were compared with surgical and histopathology results. Results were compared in terms of T staging, N staging and response to neoadjuvant therapy among MRI and surgical and pathological findings. Overall, there was good agreement between MRI and operative findings and histopathological findings.

Beyond the bowel: Wernicke's encephalopathy as a neurological complication of Crohn's disease: A case report.

Wernicke encephalopathy (WE) is a rare but severe neurological syndrome characterized, in its classic form, by the acute onset of ocular disturbances, ataxia, and cognitive impairment. It is caused by a deficiency of thiamine (vitamin B1) and mainly affects chronic alcoholics, although it can also affect patients with pathologies that lead to malnutrition. We present a case of a 58-year-old woman, who presented with significant weight loss over the past 6 months and who came to the emergency department for episodes of repetitive vomiting and a sleepy state. The patient underwent blood chemistry tests and a brain CT scan, which revealed symmetrical and bilateral hypodensity of the medial portion of the thalamus, tectal plate, and periaqueductal gray matte, suggestive of WE. She was subsequently referred to the Department of Neurology and underwent a brain MRI, which confirmed the clinical suspicion. She also had an abdominal CT scan and ileo-colonoscopy and was diagnosed with Crohn's disease. Immediately after the clinical diagnosis of WE, a replacement therapy based on intravenous thiamine at high doses was promptly set up, and the patient improved from a clinical point of view. Wernicke encephalopathy can be difficult to diagnose when it occurs in non-alcoholic patients; WE associated with IBD is a rare condition, and it can present with atypical and more subtle symptoms. Radiologists and physicians must be aware of this condition and imaging findings for rapid diagnosis and treatment.

An incidental large adrenal schwannoma: A case report.

Adrenal schwannoma is a rare tumor of Schwann cell origin that represents less than 0.2% of all adrenal tumors. These typically benign tumors are most often found in the head, neck, and limbs. However, schwannomas can also rarely occur rarely in the adrenal gland within the retroperitoneal cavity. In the adrenal gland, these tumors arise from the medulla and are difficult to diagnose, often misdiagnosed as other benign or malignant entities. In this article, we report the case of a 43-year-old female with a large left adrenal mass revealed by biopsy to be a schwannoma. We focus on the use of radiological imaging modalities and immunohistochemical analysis to optimize diagnosis and treatment intervention of this rare tumor.

Gadoxetic Acid in MRI: A Five-Year Experience at a High-Complexity Hospital in Colombia.

Objective The objective of the study was to evaluate the use of the hepatospecific contrast agent, gadoxetic acid, for MRI in patients at a high-complexity hospital in Medellin, Colombia, from 2016 to 2022. Materials and methods This was an observational, descriptive, and retrospective cross-sectional study involving patients who had undergone MRI with gadoxetic acid from February 2016 to January 2022. The MRI studies were interpreted by two radiologists specializing in body imaging, each with at least 10 years of experience. The medical records of the identified patients were reviewed. Quantitative variables were presented using either means and standard deviations or medians and interquartile ranges, depending on the distribution of the variables. Qualitative variables were represented through absolute and relative frequencies. Results A total of 100 pharmacy records were collected, leading to a final sample of 75 patients aged between three and 91 years. The primary reason for imaging was to assess focal liver lesions in 58 patients (77.3%), with bile duct injury being the second most common indication in 16 patients (21.3%). A diagnostic alteration was noted in 69.3% of cases (52 patients). Among the 58 focal liver lesions analyzed using a hepatospecific agent, 31 cases (53.4%) were diagnosed as focal nodular hyperplasia. Conclusion Our study reinforces the clinical value of gadoxetic acid-enhanced MRI in refining diagnostic assessments, particularly in cases involving bile duct and focal hepatic lesions.

Neurological Conundrum: A Case of Cerebellar Hemispheric Enlargement and Atypical Symptoms.

Cerebellar hemispheric enlargement with atypical neurological symptoms poses diagnostic challenges in clinical practice. We present the case of a 57-year-old female with persistent headache, left facial paraesthesia, dysarthria, gait ataxia, and longstanding neck swelling. Imaging studies revealed enlargement of the left cerebellar hemisphere with associated mass effect and compression of adjacent structures. The underlying etiology remained uncertain despite extensive evaluation, including magnetic resonance imaging and angiography. Differential diagnoses included neoplastic, vascular, inflammatory, and metabolic etiologies, but none fully accounted for the clinical findings. Management strategies focused on symptomatic relief and close monitoring. This case underscores the complexity of diagnosing and managing patients with rare neurological manifestations and highlights the need for continued research and collaborative approaches in optimising patient care.

Accurate preoperative diagnosis of a Rathke cleft cyst with the aid of a novel classification for sellar cystic lesions and a diagnostic algorithm decision: Tools for differentiating cystic sellar lesions with a representative case.

Background: Rathke's cleft cyst (RCC) is a benign lesion in the sellar and suprasellar compartments. Similarly, pituitary adenomas can present with cystic morphology, making it a differential diagnosis when evaluating a patient with a cystic lesion in the sellar region. Surgical goals differ between RCCs and pituitary adenomas as the first can achieve remission of symptoms with cyst decompression in contrast to pituitary adenomas where complete resection would be the main goal. Imaging analysis alone may not be sufficient to define a preoperative surgical plan. The combination of imaging and conjoined use of validated tools may provide valuable insights to the clinician when defining a surgical approach. Case Description: We present a case of a 27-year-old male with a 3-month history of visual disturbances and headaches. Magnetic resonance imaging showed a cystic lesion in the sellar compartment with compression of nearby structures. The authors were able to accurately diagnose this sellar lesion as an RCC with the conjoined aid of two classifications proposed in the literature. Cyst evacuation was performed with relief of symptoms and improved visual outcomes at follow-up. Conclusion: While cystic adenomas can require total resection for cure, RCCs can show marked improvement with partial resection and evacuation of its contents. An accurate preoperative diagnosis can lead the surgeon to opt for the best surgical approach.

Akinetic mutism following bilateral parasagittal meningioma occupied supplementary motor area removal and the spontaneous recovery of symptoms.

Background: Resection of bilateral parasagittal meningiomas of the dominant cortex is challenging. Some postoperative consequences are difficult to predict due to their low incidence. However, it is essential to recognize reversible symptoms. Akinetic mutism is a devastating but reversible symptom that occurs after supplementary motor area (SMA) injury. This report aims to provide more information to support the clinical progression of this syndrome. Case Description: A 47-year-old woman presented with psychomotor retardation and subtle weakness, particularly on the left side. A palpable mass was identified at the head vertex. Magnetic resonance imaging revealed bilateral parasagittal meningiomas with bone and sinus invasion of the SMA. A craniotomy was performed to remove the intracapsular tumor. Two days after the operation, the patient developed gradual deterioration in her motor function until it became a lock-in-like syndrome. Then, 1.5 months after treatment in the hospital and rehabilitation unit, she gradually improved her motor, cognitive, and psychomotor skills. Total recovery was achieved after 1 year. Conclusion: Surgery for lesions involving bilateral SMA can cause akinetic mutism. The typical manifestation of this syndrome may be devastating. However, it is reversible, and patients can regain full motor and cognitive functions over time without specific treatments. It is crucial to persevere and continue to provide the best care to the patient until recovery.

Unsupervised MRI motion artifact disentanglement: introducing MAUDGAN.

OBJECTIVE: This study developed an unsupervised motion artifact reduction method for MRI images of patients with brain tumors. The proposed novel design uses multi-parametric multicenter contrast-enhanced T1W (ceT1W) and T2-FLAIR MRI images. Approach: The proposed framework included two generators, two discriminators, and two feature extractor networks. A 3-fold cross-validation was used to train and fine-tune the hyperparameters of the proposed model using 230 brain MRI images with tumors, which were then tested on 148 patients' in-vivo datasets. An ablation was performed to evaluate the model's compartments. Our model was compared with Pix2pix and CycleGAN. Six evaluation metrics were reported, including normalized mean squared error (NMSE), structural similarity index (SSIM), multi-scale-SSIM (MS-SSIM), peak signal-to-noise ratio (PSNR), visual information fidelity (VIF), and multi-scale gradient magnitude similarity deviation (MS-GMSD). Artifact reduction and consistency of tumor regions, image contrast, and sharpness were evaluated by three evaluators using Likert scales and compared with ANOVA and Tukey's HSD tests. Main results: On average, our method outperforms comparative models to remove heavy motion artifacts with the lowest NMSE (18.34±5.07%) and MS-GMSD (0.07±0.03) for heavy motion artifact level. Additionally, our method creates motion-free images with the highest SSIM (0.93±0.04), PSNR (30.63±4.96), and VIF (0.45±0.05) values, along with comparable MS-SSIM (0.96±0.31). Similarly, our method outperformed comparative models in removing in-vivo motion artifacts for different distortion levels except for MS- SSIM and VIF, which have comparable performance with CycleGAN. Moreover, our method had a consistent performance for different artifact levels. For the heavy level of motion artifacts, our method got the highest Likert scores of 2.82±0.52, 1.88±0.71, and 1.02±0.14 (p-values<<0.0001) for our method, CycleGAN, and Pix2pix respectively. Similar trends were also found for other motion artifact levels. Significance: Our proposed unsupervised method was demonstrated to reduce motion artifacts from the ceT1W brain images under a multi-parametric framework.